Quickstart

Run Agent Stream, route your first execution through it, and add guardrails from the dashboard.

Deploy Agent Stream appliance→

Deploy Agent Stream appliance using Affinidi Portal to get started.

Create your first LLM Surface→

Create your first LLM Surface in the Agent Stream dashboard, connect it to OpenAI, and send a real chat completion request in under five minutes.

Add guardrails and a budget→

Add Prompt Guard PII masking and a monthly spend ceiling to the surface you created in “Create your first LLM Surface”.

Monitor your surface→

Use the surface Monitoring tab, response headers, and the rejection breakdown to see your test requests, confirm cost tracking, and learn where to look when something goes wrong.

Glossary→

Canonical terms used throughout the Agent Stream documentation.